Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     привы
    -0.06
    .--
    -0.06
     concurrently
    -0.06
     Trou
    -0.06
     -
    -0.06
    816
    -0.06
    재
    -0.06
    adioButton
    -0.06
     Evalu
    -0.06
    avi
    -0.06
    POSITIVE LOGITS
    (
    0.08
    ี↵
    0.07
    ическим
    0.07
    -themed
    0.07
    pheric
    0.07
    ecake
    0.07
    ()↵↵↵
    0.07
    pherd
    0.07
    .bold
    0.07
    ้↵
    0.06
    Act Density 0.018%

    No Known Activations